Clinical Predictor Based on Multiple Machine Learning Models

2. The method of claim 1, wherein the first subset of the plurality of data categories and the second subset of the plurality of data categories include at least one common data category.

3. The method of claim 1, wherein the data categories comprise at least one of: biography data of the particular patient, results of one or more chemical tests of the particular patient, biopsy image data of the particular patient, molecular biomarkers of the particular patient, a tumor site of the particular patient, or a tumor stage of the particular patient.

5. The method of claim 1, wherein the clinical prediction comprises predicting a survival rate of the particular patient at a pre-determined time from when the particular patient is diagnosed of having a tumor at an advanced stage.

6. The method of claim 5, further comprising determining a treatment for the particular patient based on at least the predicted survival rate.

8. The method of claim 5, wherein the first machine learning model and the second machine learning model comprise at least one of: a random forest model, or a hazard function.

10. The method of claim 8, wherein the first machine learning model comprises a hazard function which outputs a probability of non-survival of the particular patient at the pre-determined time, the hazard function being a function of values of the first subset of the plurality of data categories of biological or behavioral characteristics or treatment history.

11. The method of claim 10, wherein the first clinical performance metric value and the second clinical performance metric value refer to rates of correct prediction of survival and rates of false prediction of survival by the first machine learning model and the second machine learning model for a group of patients at the pre-determined time.

13. The method of claim 12, wherein the combined clinical prediction result represents a linear combination of the first clinical prediction result scaled by the first weight and the second clinical prediction result scaled by the second weight.